© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25205
    Prev
    Next
    INDEX
    Explanations

    the word "to" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    77
    +0.12
    0.6%
    326
    +0.11
    0.6%
    435
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.05
    109
    +0.11
    0.04
    434
    +0.11
    0.04
    Negative Logits
    ·
    -3.85
    µ
    -3.68
    ↵↵
    -3.48
            ↵
    -3.48
    -3.48
    -3.48
     ↵
    -3.48
    č↵
    -3.48
    <|outofrange|>
    -3.48
    <|outofrange|>
    -3.48
    POSITIVE LOGITS
     tomorrow
    1.58
    orel
    1.53
    els
    1.46
     Railroad
    1.45
    essee
    1.43
    atural
    1.41
     Copyright
    1.41
     nig
    1.38
     tune
    1.36
    $$\
    1.34
    Activations Density 0.028%

    No Known Activations